MACK is an Embodied Conversation Agent (ECA) who can answer questions about and give directions to the Media Lab's various research groups, projects, and people. MACK uses a combination of speech, gesture, and reference to a normal paper map that users place on a table between themselves and MACK.

Research issues involve users' differential attention to hand gestures, speech and the map, and how reference using these modalities can be fused in input and generation.

• Prof. Justine Cassell
• Tom Stocky
• Ian Gouldstone
• Gabe Reinstein

• Stocky, T. (2002). "Conveying Routes: Multimodal Generation and Spatial Intelligence in Embodied Conversational Agents." M.Eng. Thesis, Electrical Engineering and Computer Science. May 24, Massachusetts Institute of Technology, Cambridge, MA. [PDF]



• Cassell, J., Stocky, T., Bickmore, T., Gao, Y., Nakano, Y., Ryokai, K., Tversky, D., Vaucelle, C., Vilhjįlmsson, H. (2002). "MACK: Media lab Autonomous Conversational Kiosk." Proceedings of Imagina '02. February 12-15, Monte Carlo. [Abstract] [PDF]



• Stocky, T. and Cassell, J.(2002). "Shared Reality: Spatial Intelligence in Intuitive User Interfaces" Proceedings of Intelligent User Interfaces. Jan 13-16, San Francisco, CA, pp. 224-225. [Abstract] [PDF]

• Gesture and Narrative Language Group